A directive based hybrid Met Office NERC Cloud model

TL;DR

This paper introduces a hybrid GPU-accelerated version of the MONC atmospheric model, demonstrating performance improvements and energy efficiency benefits for large-scale weather and climate simulations.

Contribution

It presents a novel hybrid implementation of MONC using OpenACC, offloading intensive computations to GPUs, and evaluates its performance and energy efficiency.

Findings

Hybrid MONC shows performance gains on GPU-accelerated systems.

GPU version reduces energy consumption compared to CPU-only.

The approach is applicable to other weather and climate models.

Abstract

Large Eddy Simulation is a critical modelling tool for the investigation of atmospheric flows, turbulence and cloud microphysics. The models used by the UK atmospheric research community are homogeneous and the latest model, MONC, is designed to run on substantial HPC systems with very high CPU core counts. In order to future proof these codes it is worth investigating other technologies and architectures which might support the communities running their codes at the exa-scale. In this paper we present a hybrid version of MONC, where the most computationally intensive aspect is offloaded to the GPU while the rest of the functionality runs concurrently on the CPU. Developed using the directive driven OpenACC, we consider the suitability and maturity of this technology to modern Fortran scientific codes as well general software engineering techniques which aid this type of porting work. The performance of our hybrid model at scale is compared against the CPU version before considering other tuning options and making a comparison between the energy usage of the homo- and hetero-geneous versions. The result of this work is a promising hybrid model that shows performance benefits of our approach when the GPU has a significant computational workload which can not only be applied to the MONC model but also other weather and climate simulations in use by the community.